Modelpublic

mlx-community/Moonlight-16B-A3B-Instruct-4-bit

sourceHugging Facemitupdated 2y agoView on Hugging Face

4likes177downloads

Model Card

mlx-community/Moonlight-16B-A3B-Instruct-4-bit

The Model mlx-community/Moonlight-16B-A3B-Instruct-4-bit was converted to MLX format from moonshotai/Moonlight-16B-A3B-Instruct using mlx-lm version 0.21.5.

Use with mlx

bash

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Moonlight-16B-A3B-Instruct-4-bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)